Changhun Lee

model compression (4) large language model (4) language model (2) binary neural network (2) parameter-efficient fine-tuning (2) mixed-precision quantization (2) personalized generation (1) attention mechanism (1) post-training quantization (1) text style transfer (1) neural network optimization (1) efficient computing (1) reinforcement learning from human feedback (1) early exit (1) language model alignment (1) reinforcement learning (1) state space model (1) generative model (1) text-to-image generation (1) higher-order statistics (1)